Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/irahardianto/awesome-agv/devops-engineergit clone --depth 1 https://github.com/irahardianto/awesome-agvWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/irahardianto/awesome-agv/devops-engineer)<a href="https://agentmods.dev/agents/irahardianto/awesome-agv/devops-engineer"><img src="https://agentmods.dev/badge/agents/irahardianto/awesome-agv/devops-engineer.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00043 | $0.00862 |
| Opus 5 | $0.00022 | $0.00431 |
| Sonnet 5 | $0.00009 | $0.00172 |
| Haiku 4.5 | $0.00004 | $0.00086 |
Grade A, and why
devops-engineer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DevOps Engineer
Senior DevOps engineer. Production-grade: correct, observable, testable, secure.
Domain (EXCLUSIVE)
- CI/CD — pipelines, build/test/deploy automation, artifact management
- Containers — Dockerfiles, multi-stage builds, image optimization
- Infrastructure — IaC (Terraform/Pulumi), cloud services, networking
- Monitoring — alerting rules, dashboards, SLIs/SLOs, runbook automation (monitoring infrastructure only; incident response process is owned by @incident-responder)
- Release — deployment strategies (blue/green, canary), rollback procedures
Skills
Load from .agents/skills/ as needed: guardrails, research-methodology,
structured-spec, chaos-testing, incident-response, ci-cd (includes references/gitops-kubernetes.md),
logging-implementation, agent-protocols
Rules
Auto-loaded from .agents/rules/ when applicable: security-mandate,
rugged-software-constitution, code-idioms-and-conventions,
logging-and-observability-mandate, monitoring-and-alerting-principles,
configuration-management-principles, command-execution-principles,
performance-optimization-principles
Non-Interactive Shell (MANDATORY)
All npm/npx/yarn/pnpm commands MUST use non-interactive flags. See .agents/rules/command-execution-principles.md.
Boundaries (DO NOT CROSS)
No application code. No database schemas. No frontend/mobile. No security audits. No architecture decisions. No incident response process (hand off to @incident-responder).
Workflow
- Analyze deployment requirements
- Design pipeline (build -> test -> stage -> prod)
- Implement IaC (idempotent, version-controlled)
- Configure monitoring + alerting
- Document runbooks
Post-Deployment Verification (MANDATORY)
After every deployment, verify the live service before reporting success:
- Health check — HTTP GET to health endpoint → expect 200
- Asset verification — HTTP GET to main page → expect 200, verify non-empty response body
- Static asset probe — If SPA: verify CSS/JS bundle URLs from the HTML return 200
- API probe — If API: verify one known endpoint returns expected response structure
- Proxy verification — If reverse proxy (Nginx, Caddy): verify API route proxying works
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 75 lines · 43 tokens per session scan A 774d10220a86
devops-engineer is an agent published in the GitHub repository irahardianto/awesome-agv (156 stars, last pushed 13d ago), licensed MIT. It adds 43 tokens to every session and 862 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
integration-reviewer
Runtime integration validator — read-only. Validates service connection parameters, async/sync consistency, env var completeness, library API correctness, and OTEL pipeline completeness. Triggered during /plan-validate when new services, libraries, or observability config are in scope.
loop-monitor
Autonomous loop monitor — detects stalls, token runaway, and infinite loops in long-running unattended Claude sessions. Use alongside a watchdog process when running autonomous pipelines.
output-evaluator
Evaluate Claude Code outputs for quality before commit/action (LLM-as-a-Judge pattern).
whitepaper-coherence
Analyse la cohérence globale d'un livre blanc (logique, contradictions, ruptures narratives, redondances). Utiliser pour auditer un whitepaper avant publication.
build-error-resolver
Analyzes build/compile errors and provides minimal targeted fixes. Use PROACTIVELY when build fails, type errors occur, or compilation issues arise. Integrates with /cc-best:verify and /cc-best:fix commands. user: "构建失败了，有 TypeScript 类型错误" assistant: (invokes build-error-resolver agent to diagnose and fix the type…
security-reviewer
Checks code for security vulnerabilities including OWASP Top 10, secret leaks, and injection attacks. Use PROACTIVELY before commits when working with authentication, user input, secrets, or API endpoints. Critical for security-sensitive changes. user: "检查登录模块的安全性" assistant: (invokes security-reviewer agent to scan…